Add check_blocklist to z_fetch_url and post_url

- Standard compliance
This commit is contained in:
Hypolite Petovan 2017-04-25 22:59:11 -04:00
parent c7e1a8e871
commit 8d469c155a

View file

@ -63,15 +63,19 @@ function fetch_url($url,$binary = false, &$redirects = 0, $timeout = 0, $accept_
* string 'body' => fetched content * string 'body' => fetched content
*/ */
function z_fetch_url($url, $binary = false, &$redirects = 0, $opts = array()) { function z_fetch_url($url, $binary = false, &$redirects = 0, $opts = array()) {
$ret = array('return_code' => 0, 'success' => false, 'header' => '', 'body' => '');
$ret = array('return_code' => 0, 'success' => false, 'header' => "", 'body' => "");
$stamp1 = microtime(true); $stamp1 = microtime(true);
$a = get_app(); $a = get_app();
if (! check_domain_blocklist($url)) {
logger('z_fetch_url: domain of ' . $url . ' is blocked', LOGGER_DATA);
return $ret;
}
$ch = @curl_init($url); $ch = @curl_init($url);
if (($redirects > 8) || (!$ch)) { if (($redirects > 8) || (!$ch)) {
return $ret; return $ret;
} }
@ -89,7 +93,7 @@ function z_fetch_url($url,$binary = false, &$redirects = 0, $opts=array()) {
if (x($opts, 'accept_content')) { if (x($opts, 'accept_content')) {
curl_setopt($ch, CURLOPT_HTTPHEADER, array( curl_setopt($ch, CURLOPT_HTTPHEADER, array(
"Accept: " . $opts['accept_content'] 'Accept: ' . $opts['accept_content']
)); ));
} }
@ -97,6 +101,7 @@ function z_fetch_url($url,$binary = false, &$redirects = 0, $opts=array()) {
@curl_setopt($ch, CURLOPT_USERAGENT, $a->get_useragent()); @curl_setopt($ch, CURLOPT_USERAGENT, $a->get_useragent());
$range = intval(Config::get('system', 'curl_range_bytes', 0)); $range = intval(Config::get('system', 'curl_range_bytes', 0));
if ($range > 0) { if ($range > 0) {
@curl_setopt($ch, CURLOPT_RANGE, '0-' . $range); @curl_setopt($ch, CURLOPT_RANGE, '0-' . $range);
} }
@ -104,9 +109,11 @@ function z_fetch_url($url,$binary = false, &$redirects = 0, $opts=array()) {
if (x($opts, 'headers')) { if (x($opts, 'headers')) {
@curl_setopt($ch, CURLOPT_HTTPHEADER, $opts['headers']); @curl_setopt($ch, CURLOPT_HTTPHEADER, $opts['headers']);
} }
if (x($opts, 'nobody')) { if (x($opts, 'nobody')) {
@curl_setopt($ch, CURLOPT_NOBODY, $opts['nobody']); @curl_setopt($ch, CURLOPT_NOBODY, $opts['nobody']);
} }
if (x($opts, 'timeout')) { if (x($opts, 'timeout')) {
@curl_setopt($ch, CURLOPT_TIMEOUT, $opts['timeout']); @curl_setopt($ch, CURLOPT_TIMEOUT, $opts['timeout']);
} else { } else {
@ -119,20 +126,26 @@ function z_fetch_url($url,$binary = false, &$redirects = 0, $opts=array()) {
$check_cert = get_config('system', 'verifyssl'); $check_cert = get_config('system', 'verifyssl');
@curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, (($check_cert) ? true : false)); @curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, (($check_cert) ? true : false));
if ($check_cert) { if ($check_cert) {
@curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 2); @curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 2);
} }
$prx = get_config('system','proxy'); $proxy = get_config('system', 'proxy');
if(strlen($prx)) {
if (strlen($proxy)) {
@curl_setopt($ch, CURLOPT_HTTPPROXYTUNNEL, 1); @curl_setopt($ch, CURLOPT_HTTPPROXYTUNNEL, 1);
@curl_setopt($ch, CURLOPT_PROXY, $prx); @curl_setopt($ch, CURLOPT_PROXY, $proxy);
$prxusr = @get_config('system','proxyuser'); $proxyuser = @get_config('system', 'proxyuser');
if(strlen($prxusr))
@curl_setopt($ch, CURLOPT_PROXYUSERPWD, $prxusr); if (strlen($proxyuser)) {
@curl_setopt($ch, CURLOPT_PROXYUSERPWD, $proxyuser);
} }
if($binary) }
if ($binary) {
@curl_setopt($ch, CURLOPT_BINARYTRANSFER, 1); @curl_setopt($ch, CURLOPT_BINARYTRANSFER, 1);
}
$a->set_curl_code(0); $a->set_curl_code(0);
@ -140,6 +153,7 @@ function z_fetch_url($url,$binary = false, &$redirects = 0, $opts=array()) {
// if it throws any errors. // if it throws any errors.
$s = @curl_exec($ch); $s = @curl_exec($ch);
if (curl_errno($ch) !== CURLE_OK) { if (curl_errno($ch) !== CURLE_OK) {
logger('fetch_url error fetching ' . $url . ': ' . curl_error($ch), LOGGER_NORMAL); logger('fetch_url error fetching ' . $url . ': ' . curl_error($ch), LOGGER_NORMAL);
} }
@ -167,20 +181,25 @@ function z_fetch_url($url,$binary = false, &$redirects = 0, $opts=array()) {
$a->set_curl_headers($header); $a->set_curl_headers($header);
if ($http_code == 301 || $http_code == 302 || $http_code == 303 || $http_code == 307) { if ($http_code == 301 || $http_code == 302 || $http_code == 303 || $http_code == 307) {
$new_location_info = @parse_url($curl_info["redirect_url"]); $new_location_info = @parse_url($curl_info['redirect_url']);
$old_location_info = @parse_url($curl_info["url"]); $old_location_info = @parse_url($curl_info['url']);
$newurl = $curl_info["redirect_url"]; $newurl = $curl_info['redirect_url'];
if (($new_location_info["path"] == "") AND ($new_location_info["host"] != "")) if (($new_location_info['path'] == '') AND ( $new_location_info['host'] != '')) {
$newurl = $new_location_info["scheme"]."://".$new_location_info["host"].$old_location_info["path"]; $newurl = $new_location_info['scheme'] . '://' . $new_location_info['host'] . $old_location_info['path'];
}
$matches = array(); $matches = array();
if (preg_match('/(Location:|URI:)(.*?)\n/i', $header, $matches)) { if (preg_match('/(Location:|URI:)(.*?)\n/i', $header, $matches)) {
$newurl = trim(array_pop($matches)); $newurl = trim(array_pop($matches));
} }
if(strpos($newurl,'/') === 0)
$newurl = $old_location_info["scheme"]."://".$old_location_info["host"].$newurl; if (strpos($newurl, '/') === 0) {
$newurl = $old_location_info['scheme'] . '://' . $old_location_info['host'] . $newurl;
}
if (filter_var($newurl, FILTER_VALIDATE_URL)) { if (filter_var($newurl, FILTER_VALIDATE_URL)) {
$redirects++; $redirects++;
@curl_close($ch); @curl_close($ch);
@ -188,44 +207,42 @@ function z_fetch_url($url,$binary = false, &$redirects = 0, $opts=array()) {
} }
} }
$a->set_curl_code($http_code); $a->set_curl_code($http_code);
$a->set_curl_content_type($curl_info['content_type']); $a->set_curl_content_type($curl_info['content_type']);
$body = substr($s, strlen($header)); $body = substr($s, strlen($header));
$rc = intval($http_code); $rc = intval($http_code);
$ret['return_code'] = $rc; $ret['return_code'] = $rc;
$ret['success'] = (($rc >= 200 && $rc <= 299) ? true : false); $ret['success'] = (($rc >= 200 && $rc <= 299) ? true : false);
$ret['redirect_url'] = $url; $ret['redirect_url'] = $url;
if (!$ret['success']) { if (!$ret['success']) {
$ret['error'] = curl_error($ch); $ret['error'] = curl_error($ch);
$ret['debug'] = $curl_info; $ret['debug'] = $curl_info;
logger('z_fetch_url: error: ' . $url . ': ' . $ret['error'], LOGGER_DEBUG); logger('z_fetch_url: error: ' . $url . ': ' . $ret['error'], LOGGER_DEBUG);
logger('z_fetch_url: debug: ' . print_r($curl_info, true), LOGGER_DATA); logger('z_fetch_url: debug: ' . print_r($curl_info, true), LOGGER_DATA);
} }
$ret['body'] = substr($s, strlen($header)); $ret['body'] = substr($s, strlen($header));
$ret['header'] = $header; $ret['header'] = $header;
if (x($opts, 'debug')) { if (x($opts, 'debug')) {
$ret['debug'] = $curl_info; $ret['debug'] = $curl_info;
} }
@curl_close($ch); @curl_close($ch);
$a->save_timestamp($stamp1, "network"); $a->save_timestamp($stamp1, 'network');
return($ret); return($ret);
} }
// post request to $url. $params is an array of post variables.
/** /**
* @brief Post request to $url * @brief Send POST request to $url
* *
* @param string $url URL to post * @param string $url URL to post
* @param mixed $params * @param mixed $params array of POST variables
* @param string $headers HTTP headers * @param string $headers HTTP headers
* @param integer $redirects Recursion counter for internal use - default = 0 * @param integer $redirects Recursion counter for internal use - default = 0
* @param integer $timeout The timeout in seconds, default system config value or 60 seconds * @param integer $timeout The timeout in seconds, default system config value or 60 seconds
@ -235,12 +252,19 @@ function z_fetch_url($url,$binary = false, &$redirects = 0, $opts=array()) {
function post_url($url, $params, $headers = null, &$redirects = 0, $timeout = 0) { function post_url($url, $params, $headers = null, &$redirects = 0, $timeout = 0) {
$stamp1 = microtime(true); $stamp1 = microtime(true);
if (!check_domain_blocklist($url)) {
logger('post_url: domain of ' . $url . ' is blocked', LOGGER_DATA);
return false;
}
$a = get_app(); $a = get_app();
$ch = curl_init($url); $ch = curl_init($url);
if(($redirects > 8) || (! $ch))
return false;
logger("post_url: start ".$url, LOGGER_DATA); if (($redirects > 8) || (!$ch)) {
return false;
}
logger('post_url: start ' . $url, LOGGER_DATA);
curl_setopt($ch, CURLOPT_HEADER, true); curl_setopt($ch, CURLOPT_HEADER, true);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
@ -250,8 +274,7 @@ function post_url($url,$params, $headers = null, &$redirects = 0, $timeout = 0)
if (intval($timeout)) { if (intval($timeout)) {
curl_setopt($ch, CURLOPT_TIMEOUT, $timeout); curl_setopt($ch, CURLOPT_TIMEOUT, $timeout);
} } else {
else {
$curl_time = intval(get_config('system', 'curl_timeout')); $curl_time = intval(get_config('system', 'curl_timeout'));
curl_setopt($ch, CURLOPT_TIMEOUT, (($curl_time !== false) ? $curl_time : 60)); curl_setopt($ch, CURLOPT_TIMEOUT, (($curl_time !== false) ? $curl_time : 60));
} }
@ -265,21 +288,27 @@ function post_url($url,$params, $headers = null, &$redirects = 0, $timeout = 0)
} }
} }
} }
if($headers)
if ($headers) {
curl_setopt($ch, CURLOPT_HTTPHEADER, $headers); curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);
}
$check_cert = get_config('system', 'verifyssl'); $check_cert = get_config('system', 'verifyssl');
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, (($check_cert) ? true : false)); curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, (($check_cert) ? true : false));
if ($check_cert) { if ($check_cert) {
@curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 2); @curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 2);
} }
$prx = get_config('system','proxy');
if(strlen($prx)) { $proxy = get_config('system', 'proxy');
if (strlen($proxy)) {
curl_setopt($ch, CURLOPT_HTTPPROXYTUNNEL, 1); curl_setopt($ch, CURLOPT_HTTPPROXYTUNNEL, 1);
curl_setopt($ch, CURLOPT_PROXY, $prx); curl_setopt($ch, CURLOPT_PROXY, $proxy);
$prxusr = get_config('system','proxyuser'); $proxyuser = get_config('system', 'proxyuser');
if(strlen($prxusr)) if (strlen($proxyuser)) {
curl_setopt($ch, CURLOPT_PROXYUSERPWD, $prxusr); curl_setopt($ch, CURLOPT_PROXYUSERPWD, $proxyuser);
}
} }
$a->set_curl_code(0); $a->set_curl_code(0);
@ -293,7 +322,7 @@ function post_url($url,$params, $headers = null, &$redirects = 0, $timeout = 0)
$curl_info = curl_getinfo($ch); $curl_info = curl_getinfo($ch);
$http_code = $curl_info['http_code']; $http_code = $curl_info['http_code'];
logger("post_url: result ".$http_code." - ".$url, LOGGER_DATA); logger('post_url: result ' . $http_code . ' - ' . $url, LOGGER_DATA);
$header = ''; $header = '';
@ -310,27 +339,31 @@ function post_url($url,$params, $headers = null, &$redirects = 0, $timeout = 0)
$matches = array(); $matches = array();
preg_match('/(Location:|URI:)(.*?)\n/', $header, $matches); preg_match('/(Location:|URI:)(.*?)\n/', $header, $matches);
$newurl = trim(array_pop($matches)); $newurl = trim(array_pop($matches));
if(strpos($newurl,'/') === 0)
$newurl = $old_location_info["scheme"] . "://" . $old_location_info["host"] . $newurl; if (strpos($newurl, '/') === 0) {
$newurl = $old_location_info['scheme'] . '://' . $old_location_info['host'] . $newurl;
}
if (filter_var($newurl, FILTER_VALIDATE_URL)) { if (filter_var($newurl, FILTER_VALIDATE_URL)) {
$redirects++; $redirects++;
logger("post_url: redirect ".$url." to ".$newurl); logger('post_url: redirect ' . $url . ' to ' . $newurl);
return post_url($newurl, $params, $headers, $redirects, $timeout); return post_url($newurl, $params, $headers, $redirects, $timeout);
//return fetch_url($newurl,false,$redirects,$timeout);
} }
} }
$a->set_curl_code($http_code); $a->set_curl_code($http_code);
$body = substr($s, strlen($header)); $body = substr($s, strlen($header));
$a->set_curl_headers($header); $a->set_curl_headers($header);
curl_close($ch); curl_close($ch);
$a->save_timestamp($stamp1, "network"); $a->save_timestamp($stamp1, 'network');
logger("post_url: end ".$url, LOGGER_DATA); logger('post_url: end ' . $url, LOGGER_DATA);
return($body); return $body;
} }
// Generic XML return // Generic XML return